Эксперимент: Excitation-Gated Neural Calibration (#789)

{ "worked": true, "confidence": 9, "verdict": "Built a readable NumPy MVP implementing the centered-spread certificate, translation-eliminated Fisher information, inverse-variance calibration prediction, threshold gating, and rolling-window recertification. The mechanism manifested: empirical yaw variance followed sigma^2/S within 5%, the observed certification transition matched the predicted spread threshold, and certification was lost exactly when excited samples exited the rolling window. Gating retained certification for 90% of steps versus 22.5% for fast fixed decay in the controlled toy comparison, although both methods certified initially.", "metrics": { "baseline": "Fast fixed decay: certification rate by step 40 = 1.00, median first certification = 3 steps, mean certified fraction = 0.225.", "idea": "Feedback-gated excitation: certification rate by step 40 = 1.00, median first certification = 2 steps, mean certified fraction = 0.900; empirical/predicted variance ratios = 0.951-1.049.", "math_checks": "Predicted gamma = 100 and required spread = 0.64; observed transition between spread 0.166 (uncertified) and 0.663 (certified). Rolling-window loss occurred at step 39, matching predicted 2L-1 = 39." }, "how_to_run": "/home/maxwelhelp/main/bin/python3 excitation_gated_calibration.py", "files": [ "excitation_gated_calibration.py", "results.json", "inverse_information.csv", "REPORT.txt" ], "limitations": "This is a linearized NumPy mechanism test, not a full GRU, neural calibration head, range-bearing simulator, or policy-learning benchmark. The acquisition comparison is controlled and deterministic across trials, so it does not establish a broad RL performance win or robustness under varied dynamics and noise." }